Skip to main content

Table 1 – Statistics of the relation extraction dataset (a subset from the 2010 i2b2/VA challenge)

From: Integrating shortest dependency path and sentence sequence into a deep learning framework for relation extraction in clinical text

Relation type

Description

Number of instances

TeCP

Test conducted to investigate medical problem

504

TeRP

Test reveals medical problem

3052

PIP

Medical problem indicates medical problem

2203

TrCP

Treatment causes medical problem

526

TrAP

Treatment is administered for medical problem

2617

TrWP

Treatment worsens medical problem

133

TrNAP

Treatment is not administered because of medical problem

174

TrIP

Treatment improves medical problem

203

None

No relation between target entities

19,870

Total

–

29,282